We consider the problem of constrained Markov decision process (CMDP) in continuous state-actions spaces where the goal is to maximize the expected cumulative reward subject to some constraints. We propose a novel Conservative Natural Policy Gradient Primal-Dual Algorithm (C-NPG-PD) to achieve zero constraint violation while achieving state of the art convergence results for the objective value function. For general policy parametrization, we prove convergence of value function to global optimal upto an approximation error due to restricted policy class. We even improve the sample complexity of existing constrained NPG-PD algorithm \cite{Ding2020} from $\mathcal{O}(1/ε^6)$ to $\mathcal{O}(1/ε^4)$. To the best of our knowledge, this is the first work to establish zero constraint violation with Natural policy gradient style algorithms for infinite horizon discounted CMDPs. We demonstrate the merits of proposed algorithm via experimental evaluations.
Purdue University（普渡大学）；US Army Research Laboratory（美国陆军研究实验室）
Reinforcement learning is widely used in applications where one needs to perform sequential decisions while interacting with the environment. The problem becomes more challenging when the decision requirement includes satisfying some safety constraints. The problem is mathematically formulated as constrained Markov decision process (CMDP). In the literature, various algorithms are available to solve CMDP problems in a model-free manner to achieve $ε$-optimal cumulative reward with $ε$ feasible policies. An $ε$-feasible policy implies that it suffers from constraint violation. An important ques…
We address the problem of finding the optimal policy of a constrained Markov decision process (CMDP) using a gradient descent-based algorithm. Previous results have shown that a primal-dual approach can achieve an $\mathcal{O}(1/\sqrt{T})$ global convergence rate for both the optimality gap and the constraint violation. We propose a new algorithm called policy mirror descent-primal dual (PMD-PD) algorithm that can provably achieve a faster $\mathcal{O}(\log(T)/T)$ convergence rate for both the optimality gap and the constraint violation. For the primal (policy) update, the PMD-PD algorithm uti…
We address the issue of safety in reinforcement learning. We pose the problem in an episodic framework of a constrained Markov decision process. Existing results have shown that it is possible to achieve a reward regret of $\tilde{\mathcal{O}}(\sqrt{K})$ while allowing an $\tilde{\mathcal{O}}(\sqrt{K})$ constraint violation in $K$ episodes. A critical question that arises is whether it is possible to keep the constraint violation even smaller. We show that when a strictly safe policy is known, then one can confine the system to zero constraint violation with arbitrarily high probability while …
We consider primal-dual-based reinforcement learning (RL) in episodic constrained Markov decision processes (CMDPs) with non-stationary objectives and constraints, which plays a central role in ensuring the safety of RL in time-varying environments. In this problem, the reward/utility functions and the state transition functions are both allowed to vary arbitrarily over time as long as their cumulative variations do not exceed certain known variation budgets. Designing safe RL algorithms in time-varying environments is particularly challenging because of the need to integrate the constraint vi…
Near-Constant Strong Violation and Last-Iterate Convergence for Online CMDPs via Decaying Safety Margins
School of Informatics, University of Edinburgh, Edinburgh, United Kingdom（爱丁堡大学信息学院）；School of Mathematics, University of Edinburgh, Edinburgh, United Kingdom（爱丁堡大学数学学院）
Constrained Markov decision processes (CMDPs) model scenarios of sequential decision making with multiple objectives that are increasingly important in many applications. However, the model is often unknown and must be learned online while still ensuring the constraint is met, or at least the violation is bounded with time. Some recent papers have made progress on this very challenging problem but either need unsatisfactory assumptions such as knowledge of a safe policy, or have high cumulative regret. We propose the Safe PSRL (posterior sampling-based RL) algorithm that does not need such ass…
Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs
University of Tennessee, Knoxville（田纳西大学）；University of Maryland, College Park（马里兰大学）；Apple Inc.（苹果公司）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Southern California（南加州大学）
Peking University（北京大学）；National University of Singapore（新加坡国立大学）；Beijing International Center for Mathematical Research（北京国际数学研究中心）
As an important framework for safe Reinforcement Learning, the Constrained Markov Decision Process (CMDP) has been extensively studied in the recent literature. However, despite the rich results under various on-policy learning settings, there still lacks some essential understanding of the offline CMDP problems, in terms of both the algorithm design and the information theoretic sample complexity lower bound. In this paper, we focus on solving the CMDP problems where only offline data are available. By adopting the concept of the single-policy concentrability coefficient $C^*$, we establish a…
University of Pennsylvania（宾夕法尼亚大学）；University of Melbourne（墨尔本大学）
Reinforcement Learning (RL) agents in the real world must satisfy safety constraints in addition to maximizing a reward objective. Model-based RL algorithms hold promise for reducing unsafe real-world actions: they may synthesize policies that obey all constraints using simulated samples from a learned model. However, imperfect models can result in real-world constraint violations even for actions that are predicted to satisfy all constraints. We propose Conservative and Adaptive Penalty (CAP), a model-based safe RL framework that accounts for potential modeling errors by capturing model uncer…
Simon Fraser University（西蒙弗雷泽大学）；SAIT AI Lab（SAIT人工智能实验室）；Amii（阿尔伯塔机器智能研究所）；University of Alberta（阿尔伯塔大学）；DeepMind（深度思维）；Mila（米拉人工智能研究所）；McGill University（麦吉尔大学）
We study policy optimization in an infinite horizon, $γ$-discounted constrained Markov decision process (CMDP). Our objective is to return a policy that achieves large expected reward with a small constraint violation. We consider the online setting with linear function approximation and assume global access to the corresponding features. We propose a generic primal-dual framework that allows us to bound the reward sub-optimality and constraint violation for arbitrary algorithms in terms of their primal and dual regret on online linear optimization problems. We instantiate this framework to us…
A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees
The University of Tokyo（东京大学）；OMRON SINIC X（欧姆龙SINIC X公司）；Mizuho–DL Financial Technology（瑞穗-DL金融科技公司）；Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所革新智能综合研究中心）；Osaka University（大阪大学）；Kyoto University（京都大学）
Finite-Time Complexity of Online Primal-Dual Natural Actor-Critic Algorithm for Constrained Markov Decision Processes
School of Electrical and Computer Engineering, Georgia Institute of Technology（佐治亚理工学院电气与计算机工程学院）；Bradley Department of Electrical and Computer Engineering, Virginia Tech（弗吉尼亚理工大学布拉德利电气与计算机工程学院）
University of Michigan（密歇根大学）；University of Southern California（南加州大学）；Princeton University（普林斯顿大学）；Northwestern University（西北大学）
We consider online learning for episodic stochastically constrained Markov decision processes (CMDPs), which plays a central role in ensuring the safety of reinforcement learning. Here the loss function can vary arbitrarily across the episodes, and both the loss received and the budget consumption are revealed at the end of each episode. Previous works solve this problem under the restrictive assumption that the transition model of the Markov decision processes (MDPs) is known a priori and establish regret bounds that depend polynomially on the cardinalities of the state space $\mathcal{S}$ an…
The Ohio State University（俄亥俄州立大学）；Georgia Institute of Technology（佐治亚理工学院）
In safe reinforcement learning (SRL) problems, an agent explores the environment to maximize an expected total reward and meanwhile avoids violation of certain constraints on a number of expected total costs. In general, such SRL problems have nonconvex objective functions subject to multiple nonconvex constraints, and hence are very challenging to solve, particularly to provide a globally optimal policy. Many popular SRL algorithms adopt a primal-dual structure which utilizes the updating of dual variables for satisfying the constraints. In contrast, we propose a primal approach, called const…
Stochastic Primal Dual Coordinate Method with Non-Uniform Sampling Based on Optimality Violations
Nagoya Institute of Technology（名古屋工业大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所革新智能综合研究中心）；National Institute for Materials Science（国立材料科学研究所）
Primal-Dual Policy Optimization for Linear CMDPs with Adversarial Losses
Research Institute of Mathematics, Seoul National University（数学研究所，首尔国立大学）；Interdisciplinary Program in Artificial Intelligence, Seoul National University（人工智能跨学科项目，首尔国立大学）；Korea Institute for Advanced Study（韩国高级研究院）
Near-Optimal Primal-Dual Algorithm for Learning Linear Mixture CMDPs with Adversarial Rewards
Department of Industrial and Systems Engineering, KAIST（韩国科学技术院工业与系统工程系）；Department of Mathematical Sciences, Seoul National University（首尔大学数学科学系）；Research Institute of Mathematics, Seoul National University（首尔大学数学研究所）；Interdisciplinary Program in Artificial Intelligence, Seoul National University（首尔大学人工智能跨学科项目）；Korea Institute for Advanced Study（韩国高等研究院）
University of Southern California（南加利福尼亚大学）；Facebook Inc.（脸书公司）；Princeton University（普林斯顿大学）；Northwestern University（西北大学）
We study the Safe Reinforcement Learning (SRL) problem using the Constrained Markov Decision Process (CMDP) formulation in which an agent aims to maximize the expected total reward subject to a safety constraint on the expected total value of a utility function. We focus on an episodic setting with the function approximation where the Markov transition kernels have a linear structure but do not impose any additional assumptions on the sampling model. Designing SRL algorithms with provable computational and statistical efficiency is particularly challenging under this setting because of the nee…
Georgia Institute of Technology（佐治亚理工学院）；The Ohio State University（俄亥俄州立大学）；University at Buffalo, The State University of New York（纽约州立大学布法罗分校）
The problem of constrained Markov decision process (CMDP) is investigated, where an agent aims to maximize the expected accumulated discounted reward subject to multiple constraints on its utilities/costs. A new primal-dual approach is proposed with a novel integration of three ingredients: entropy regularized policy optimizer, dual variable regularizer, and Nesterov's accelerated gradient descent dual optimizer, all of which are critical to achieve a faster convergence. The finite-time error bound of the proposed approach is characterized. Despite the challenge of the nonconcave objective sub…
This paper studies how to train machine-learning models that directly approximate the optimal solutions of constrained optimization problems. This is an empirical risk minimization under constraints, which is challenging as training must balance optimality and feasibility conditions. Supervised learning methods often approach this challenge by training the model on a large collection of pre-solved instances. This paper takes a different route and proposes the idea of Primal-Dual Learning (PDL), a self-supervised training method that does not require a set of pre-solved instances or an optimiza…
Policy-based Primal-Dual Methods for Concave CMDP with Variance Reduction
Department of Industrial Engineering and Operations Research, UC Berkeley（加州大学伯克利分校工业工程与运筹学系）；Department of Mechanical Engineering, UC Berkeley（加州大学伯克利分校机械工程系）
ShanghaiTech University（上海科技大学）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）
This paper studies online nonstochastic control problems with adversarial and static constraints. We propose online nonstochastic control algorithms that achieve both sublinear regret and sublinear adversarial constraint violation while keeping static constraint violation minimal against the optimal constrained linear control policy in hindsight. To establish the results, we introduce an online convex optimization with memory framework under adversarial and static constraints, which serves as a subroutine for the constrained online nonstochastic control algorithms. This subroutine also achieve…
Mitsubishi Electric Research Laboratories（三菱电机研究院）；École polytechnique fédérale de Lausanne（洛桑联邦理工学院）；Swiss Federal Laboratories for Materials Science and Technology（瑞士联邦材料科学与技术实验室）
We study the problem of performance optimization of closed-loop control systems with unmodeled dynamics. Bayesian optimization (BO) has been demonstrated effective for improving closed-loop performance by automatically tuning controller gains or reference setpoints in a model-free manner. However, BO methods have rarely been tested on dynamical systems with unmodeled constraints. In this paper, we propose a violation-aware BO algorithm (VABO) that optimizes closed-loop performance while simultaneously learning constraint-feasible solutions. Unlike classical constrained BO methods which allow a…
Avoiding Structural Failure Modes in Tabular Fair SSL: Online Primal-Dual Allocation under Confidence Gating
College of Computer Science and Technology, Jilin University, China（吉林大学计算机科学与技术学院）；Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education, Jilin University, China（教育部符号计算与知识工程重点实验室）
Indian Institute of Technology Kanpur（印度理工学院坎普尔分校）；U.S. Army Research Laboratory（美国陆军研究实验室）
This paper considers stochastic convex optimization problems where the objective and constraint functions involve expectations with respect to the data indices or environmental variables, in addition to deterministic convex constraints on the domain of the variables. Although the setting is generic and arises in different machine learning applications, online and efficient approaches for solving such problems have not been widely studied. Since the underlying data distribution is unknown a priori, a closed-form solution is generally not available, and classical deterministic optimization parad…
Trinity College Dublin（都柏林圣三一学院）；TU Delft（代尔夫特理工大学）
In this paper we extend the classical Follow-The-Regularized-Leader (FTRL) algorithm to encompass time-varying constraints, through adaptive penalization. We establish sufficient conditions for the proposed Penalized FTRL algorithm to achieve $O(\sqrt{t})$ regret and violation with respect to strong benchmark $\hat{X}^{max}_t$. Lacking prior knowledge of the constraints, this is probably the largest benchmark set that we can reasonably hope for. Our sufficient conditions are necessary in the sense that when they are violated there exist examples where $O(\sqrt{t})$ regret and violation is not …
Mitsubishi Electric Research Laboratories（三菱电机研究实验室）；École polytechnique fédérale de Lausanne（洛桑联邦理工学院）；Swiss Federal Laboratories for Materials Science and Technology（瑞士联邦材料科学与技术实验室）
We study the problem of performance optimization of closed-loop control systems with unmodeled dynamics. Bayesian optimization (BO) has been demonstrated to be effective for improving closed-loop performance by automatically tuning controller gains or reference setpoints in a model-free manner. However, BO methods have rarely been tested on dynamical systems with unmodeled constraints and time-varying ambient conditions. In this paper, we propose a violation-aware contextual BO algorithm (VACBO) that optimizes closed-loop performance while simultaneously learning constraint-feasible solutions …
